skill-creator

작성자: microsoft

이 저장소에서 효과적인 GitHub Copilot 스킬(.github/skills/)을 생성하기 위한 가이드입니다. 새 스킬을 만들거나, 기존 스킬을 업데이트하거나, 또는...

npx skills add https://github.com/microsoft/vscode-documentdb --skill skill-creator

Skill Creator for GitHub Copilot

Create and maintain skills in .github/skills/ that extend GitHub Copilot's capabilities with project-specific knowledge.

What Are Skills

Skills are SKILL.md files that provide specialized, procedural knowledge that Copilot doesn't inherently have. They turn Copilot from a general assistant into a domain expert for specific tasks in this codebase.

Skills provide:

  • Specialized workflows — multi-step procedures for project-specific domains
  • Domain expertise — architecture patterns, conventions, business logic
  • Bundled references — detailed docs loaded only when needed

Skill Anatomy

.github/skills/
└── skill-name/
    ├── SKILL.md              (required — frontmatter + instructions)
    └── references/           (optional — detailed docs, loaded on demand)

SKILL.md Structure

---
name: my-skill-name
description: What this skill does and WHEN to use it. Include trigger words and scenarios. This is the primary mechanism for Copilot to decide whether to load the skill body.
---

# Skill Title

Concise instructions for using this skill.

## When to Use

- Bullet list of triggering scenarios

## Core Content

(workflow, patterns, examples)

Wiring the Skill

After creating the SKILL.md, register it in .github/copilot-instructions.md under the <skills> section:

<skill>
<name>my-skill-name</name>
<description>Same or similar description as in SKILL.md frontmatter</description>
<file>${workspaceFolder}\.github\skills\my-skill-name\SKILL.md</file>
</skill>

Note: Replace ${workspaceFolder} with the absolute path to the repository root on your machine (e.g. \home\user\repos\vscode-documentdb). VS Code resolves skill file paths at runtime and currently requires absolute paths.

Copilot reads skill metadata (name + description) to decide when to trigger. The SKILL.md body is loaded only after triggering.

Core Principles

1. Concise is Key

The context window is shared with conversation history, other instructions, and user requests. Challenge each paragraph: "Does Copilot already know this?" and "Does this justify its token cost?"

  • Prefer concise examples over verbose explanations
  • Only include what Copilot doesn't already know — skip general TypeScript/React knowledge
  • Target under 300 lines for SKILL.md body; split into references if larger

2. Progressive Disclosure

Use a three-level loading system:

  1. Metadata (name + description) — always visible (~50 words)
  2. SKILL.md body — loaded when skill triggers
  3. References — loaded on demand by Copilot when deeper detail is needed

For skills with multiple variants or extensive reference material, keep the core workflow in SKILL.md and move details to references/:

## Advanced Topics

- **Detailed format spec**: See [FORMAT.md](./FORMAT.md)
- **Migration patterns**: See [references/migration.md](./references/migration.md)

3. Match Freedom to Task Fragility

Freedom LevelWhenExample
High (text guidance)Multiple valid approachesArchitecture recommendations
Medium (patterns with examples)Preferred pattern existstRPC router creation
Low (exact steps)Fragile, error-proneRelease note formatting

4. Do NOT Include

  • README.md, CHANGELOG.md, or auxiliary documentation
  • Setup/installation instructions for the skill itself
  • User-facing documentation — skills are for Copilot, not humans
  • Information Copilot already knows (general language features, common libraries)

Skill Creation Workflow

Step 1: Understand the Domain

Identify concrete scenarios the skill addresses:

  • What tasks trigger it?
  • What does Copilot get wrong without it?
  • What project-specific knowledge is needed?

Step 2: Plan Contents

For each scenario, determine:

  • What code patterns or templates are repeatedly needed?
  • What reference material should be available?
  • What pitfalls must be called out?

Step 3: Write the Skill

  1. Create .github/skills/{skill-name}/SKILL.md
  2. Write frontmatter: name and description (description is the trigger — be comprehensive about when to use)
  3. Write body: Core workflow, patterns, examples. Keep it lean.
  4. Add references (optional): Split out detailed format specs, schemas, or variant-specific docs
  5. Register in .github/copilot-instructions.md

Step 4: Validate

  • Ensure the description covers all trigger scenarios
  • Verify code examples follow project conventions (see .github/copilot-instructions.md and .github/instructions/)
  • Check that referenced files exist and paths are correct
  • Confirm the skill doesn't duplicate information already in .github/instructions/ files

Existing Skills Reference

SkillPurpose
writing-release-notesRelease notes and changelog generation
accessibility-aria-expertAccessibility issues in React/Fluent UI webviews
webview-trpc-messagingtRPC communication between extension host and webviews

Example: Minimal Skill

---
name: my-pattern
description: Implements the XYZ pattern for this codebase. Use when creating new XYZ instances, modifying existing XYZ behavior, or debugging XYZ-related issues.
---

# XYZ Pattern

## When to Use

- Creating a new XYZ
- Modifying XYZ behavior
- Debugging XYZ issues

## Pattern

\`\`\`typescript
// core pattern example
\`\`\`

## Common Pitfalls

- Don't do X because Y
- Always do Z when W

microsoft의 다른 스킬

oss-growth
microsoft
OSS 성장 해커 페르소나
agent-framework-azure-ai-py
microsoft
Microsoft Agent Framework Python SDK(agent-framework-azure-ai)를 사용하여 Azure AI Foundry 에이전트를 구축합니다. AzureAIAgentsProvider로 지속적 에이전트를 만들 때, 호스팅 도구(코드 인터프리터, 파일 검색, 웹 검색)를 사용할 때, MCP 서버를 통합할 때, 대화 스레드를 관리할 때, 또는 스트리밍 응답을 구현할 때 사용합니다. 함수 도구, 구조화된 출력, 다중 도구 에이전트를 다룹니다.
development
airunway-aks-setup
microsoft
AKS에서 AI Runway 설정 — 빈 클러스터에서 실행 중인 모델까지. 클러스터 검증, 컨트롤러 설치, GPU 평가, 공급자 설정, 첫 배포를 다룹니다. 시기: "AI Runway 설정", "AKS 클러스터 온보딩", "AI Runway 설치", "airunway 설정", "AKS에 모델 배포", "AKS에서 GPU 추론", "AKS에서 KAITO 설정", "AKS에서 LLM 실행", "AKS에서 vLLM", "AKS에서 모델 서빙 설정", "AI Runway 컨트롤러".
devops
appinsights-instrumentation
microsoft
Azure Application Insights로 웹앱을 계측하기 위한 지침입니다. 원격 분석 패턴, SDK 설정, 구성 참조를 제공합니다. WHEN: 앱 계측 방법, App Insights SDK, 원격 분석 패턴, App Insights란 무엇인가, Application Insights 지침, 계측 예시, APM 모범 사례.
devops
applicationinsights-web-ts
microsoft
브라우저/웹 앱을 Application Insights JavaScript SDK(@microsoft/applicationinsights-web)로 계측합니다. Real User Monitoring(RUM) — 페이지 뷰, 클릭, AJAX/fetch 종속성, 예외, 사용자 지정 이벤트, 백엔드 OpenTelemetry 트레이스와 상관관계가 있는 브라우저 측 GenAI 에이전트 트레이스에 사용합니다. SDK Loader Script 및 npm 설정, 프레임워크 확장(React, React Native, Angular), Click Analytics, 텔레메트리 이니셜라이저, 브라우저에서 생성된 에이전트/도구/모델 스팬에 대한 OTel GenAI 의미론적 규칙을 다룹니다.
devops
azure-ai-anomalydetector-java
microsoft
Azure AI Anomaly Detector SDK for Java로 이상 탐지 애플리케이션을 구축하세요. 단변량/다변량 이상 탐지, 시계열 분석 또는 AI 기반 모니터링을 구현할 때 사용하세요.
development
azure-ai-language-conversations-py
microsoft
azure-ai-language-conversations Python SDK를 사용하여 대화형 언어 이해(CLU)를 구현합니다. ConversationAnalysisClient로 대화 의도와 엔터티를 분석하거나, NLP 기능을 구축하거나, 애플리케이션에 언어 이해를 통합할 때 사용합니다.
development
azure-ai-ml-py
microsoft
Azure Machine Learning SDK v2 for Python. ML 작업 영역, 작업, 모델, 데이터 세트, 컴퓨팅 및 파이프라인에 사용합니다. 트리거: "azure-ai-ml", "MLClient", "workspace", "model registry", "training jobs", "datasets".
development